Merge tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - Optimise radix KVM guest entry/exit by 2x on Power9/Power10.

 - Allow firmware to tell us whether to disable the entry and uaccess
   flushes on Power10 or later CPUs.

 - Add BPF_PROBE_MEM support for 32 and 64-bit BPF jits.

 - Several fixes and improvements to our hard lockup watchdog.

 - Activate HAVE_DYNAMIC_FTRACE_WITH_REGS on 32-bit.

 - Allow building the 64-bit Book3S kernel without hash MMU support, ie.
   Radix only.

 - Add KUAP (SMAP) support for 40x, 44x, 8xx, Book3E (64-bit).

 - Add new encodings for perf_mem_data_src.mem_hops field, and use them
   on Power10.

 - A series of small performance improvements to 64-bit interrupt entry.

 - Several commits fixing issues when building with the clang integrated
   assembler.

 - Many other small features and fixes.

Thanks to Alan Modra, Alexey Kardashevskiy, Ammar Faizi, Anders Roxell,
Arnd Bergmann, Athira Rajeev, Cédric Le Goater, Christophe JAILLET,
Christophe Leroy, Christoph Hellwig, Daniel Axtens, David Yang, Erhard
Furtner, Fabiano Rosas, Greg Kroah-Hartman, Guo Ren, Hari Bathini, Jason
Wang, Joel Stanley, Julia Lawall, Kajol Jain, Kees Cook, Laurent Dufour,
Madhavan Srinivasan, Mark Brown, Minghao Chi, Nageswara R Sastry, Naresh
Kamboju, Nathan Chancellor, Nathan Lynch, Nicholas Piggin, Nick Child,
Oliver O'Halloran, Peiwei Hu, Randy Dunlap, Ravi Bangoria, Rob Herring,
Russell Currey, Sachin Sant, Sean Christopherson, Segher Boessenkool,
Thadeu Lima de Souza Cascardo, Tyrel Datwyler, Xiang wangx, and Yang
Guang.

* tag 'powerpc-5.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (240 commits)
  powerpc/xmon: Dump XIVE information for online-only processors.
  powerpc/opal: use default_groups in kobj_type
  powerpc/cacheinfo: use default_groups in kobj_type
  powerpc/sched: Remove unused TASK_SIZE_OF
  powerpc/xive: Add missing null check after calling kmalloc
  powerpc/floppy: Remove usage of the deprecated "pci-dma-compat.h" API
  selftests/powerpc: Add a test of sigreturning to an unaligned address
  powerpc/64s: Use EMIT_WARN_ENTRY for SRR debug warnings
  powerpc/64s: Mask NIP before checking against SRR0
  powerpc/perf: Fix spelling of "its"
  powerpc/32: Fix boot failure with GCC latent entropy plugin
  powerpc/code-patching: Replace patch_instruction() by ppc_inst_write() in selftests
  powerpc/code-patching: Move code patching selftests in its own file
  powerpc/code-patching: Move instr_is_branch_{i/b}form() in code-patching.h
  powerpc/code-patching: Move patch_exception() outside code-patching.c
  powerpc/code-patching: Use test_trampoline for prefixed patch test
  powerpc/code-patching: Fix patch_branch() return on out-of-range failure
  powerpc/code-patching: Reorganise do_patch_instruction() to ease error handling
  powerpc/code-patching: Fix unmap_patch_area() error handling
  powerpc/code-patching: Fix error handling in do_patch_instruction()
  ...

1 files changed, 57 insertions, 15 deletions

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 8571aafcc9e1..9eae8d8ed340 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -297,7 +297,7 @@ asm (
 
 /* Assemble the body code between the prologue & epilogue */
 int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
-		       u32 *addrs, bool extra_pass)
+		       u32 *addrs, int pass)
 {
 	enum stf_barrier_type stf_barrier = stf_barrier_type_get();
 	const struct bpf_insn *insn = fp->insnsi;
@@ -311,6 +311,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u32 code = insn[i].code;
 		u32 dst_reg = b2p[insn[i].dst_reg];
 		u32 src_reg = b2p[insn[i].src_reg];
+		u32 size = BPF_SIZE(code);
 		s16 off = insn[i].off;
 		s32 imm = insn[i].imm;
 		bool func_addr_fixed;
@@ -778,25 +779,66 @@ emit_clear:
 		 */
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
-			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
-			if (insn_is_zext(&insn[i + 1]))
-				addrs[++i] = ctx->idx * 4;
-			break;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
-			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
-			if (insn_is_zext(&insn[i + 1]))
-				addrs[++i] = ctx->idx * 4;
-			break;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
-			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
-			if (insn_is_zext(&insn[i + 1]))
-				addrs[++i] = ctx->idx * 4;
-			break;
+		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			PPC_BPF_LL(dst_reg, src_reg, off);
+		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			/*
+			 * As PTR_TO_BTF_ID that uses BPF_PROBE_MEM mode could either be a valid
+			 * kernel pointer or NULL but not a userspace address, execute BPF_PROBE_MEM
+			 * load only if addr is kernel address (see is_kernel_addr()), otherwise
+			 * set dst_reg=0 and move on.
+			 */
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				if (IS_ENABLED(CONFIG_PPC_BOOK3E_64))
+					PPC_LI64(b2p[TMP_REG_2], 0x8000000000000000ul);
+				else /* BOOK3S_64 */
+					PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_LI(dst_reg, 0));
+				/*
+				 * Check if 'off' is word aligned because PPC_BPF_LL()
+				 * (BPF_DW case) generates two instructions if 'off' is not
+				 * word-aligned and one instruction otherwise.
+				 */
+				if (BPF_SIZE(code) == BPF_DW && (off & 3))
+					PPC_JMP((ctx->idx + 3) * 4);
+				else
+					PPC_JMP((ctx->idx + 2) * 4);
+			}
+
+			switch (size) {
+			case BPF_B:
+				EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
+				break;
+			case BPF_H:
+				EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
+				break;
+			case BPF_W:
+				EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
+				break;
+			case BPF_DW:
+				PPC_BPF_LL(dst_reg, src_reg, off);
+				break;
+			}
+
+			if (size != BPF_DW && insn_is_zext(&insn[i + 1]))
+				addrs[++i] = ctx->idx * 4;
+
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				ret = bpf_add_extable_entry(fp, image, pass, ctx, ctx->idx - 1,
+							    4, dst_reg);
+				if (ret)
+					return ret;
+			}
 			break;
 
 		/*
@@ -831,7 +873,7 @@ emit_clear:
 		case BPF_JMP | BPF_CALL:
 			ctx->seen |= SEEN_FUNC;
 
-			ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass,
+			ret = bpf_jit_get_func_addr(fp, &insn[i], false,
 						    &func_addr, &func_addr_fixed);
 			if (ret < 0)
 				return ret;